INDEX

Explanations

instances of quantitative comparisons, particularly involving the concept of "much."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<eos>

-0.56

 absolutely

-0.53

絶対に

-0.49

стро

-0.49

 perfettamente

-0.48

 perfectly

-0.46

 assolutamente

-0.46

hak

-0.46

无数

-0.45

 never

-0.45

POSITIVE LOGITS

 ExecuteAsync

0.86

########.

0.85

 насељу

0.82

PerformLayout

0.81

 resourceCulture

0.76

gameserver

0.75

存于互联网档案馆

0.75

참고

0.75

Portail

0.74

mybatisplus

0.74

Activations Density 0.413%

instances of quantitative comparisons, particularly involving the concept of "much."

No Comments

No Known Activations